Aims and Scope

Aims

The Journal of Healthcare Analytics and Informatics is an international, peer-reviewed, open-access scholarly journal that publishes original research, systematic and methodological reviews, and short communications in healthcare analytics, biomedical informatics, and data-driven health systems. The Journal serves as a platform for rigorous, applied, and theoretically grounded scholarship that addresses the design, evaluation, and governance of intelligent health information systems and the methods, data, and infrastructure that support them, with the ultimate goal of improving patient outcomes and population health.

The Journal aims to publish work that demonstrates originality, methodological rigor, reproducibility, and clearly articulated contributions to theory, method, or practice. It welcomes both single-discipline studies of high methodological quality and interdisciplinary work that draws on computer science, data science, biomedical informatics, biostatistics, and clinical research together.

Scope

The Journal's scope is organized around three subject domains. The areas listed below are indicative rather than exhaustive; submissions outside these examples but within the broad subject domains are welcome.

Clinical Analytics, Decision Support, and Diagnostic AI

The Journal welcomes research on analytical methods applied to clinical care and diagnosis, including:

  • Clinical decision support systems
  • AI-assisted diagnosis, prognosis, and risk prediction
  • Medical imaging and radiology AI
  • Digital pathology and histopathology image analysis
  • Early-warning and deterioration-detection models
  • Precision medicine and treatment personalization
  • Genomic and multi-omics informatics
  • Clinical natural language processing of notes and reports
  • Predictive modeling of disease onset and progression
  • Real-world evidence and clinical outcomes analytics

Health Informatics, Data, and Systems

The Journal welcomes research on health data, infrastructure, and the systems that deliver intelligence at scale, including:

  • Electronic health record analytics and interoperability (HL7, FHIR)
  • Health data integration, standards, and clinical terminologies
  • Epidemiological modeling and public health surveillance
  • Wearable, sensor, and remote patient monitoring analytics
  • Telemedicine and digital therapeutics analytics
  • Population health and health systems analytics
  • Federated and distributed learning across care sites
  • Clinical knowledge representation and knowledge graphs
  • Biomedical information retrieval and literature mining
  • Human factors and clinician-facing AI interfaces

Foundations, Trustworthiness, and Governance

The Journal welcomes research on the methodological and ethical foundations of health analytics, including:

  • Validation, calibration, and evaluation methodology for clinical models
  • Explainability, interpretability, and transparency of clinical AI
  • Fairness, bias mitigation, and health equity in algorithms
  • Robustness, safety, and reliability of medical AI
  • Privacy-preserving computation, security, and de-identification of health data
  • Causal inference for treatment effects and observational data
  • Reproducibility, benchmarking, and reporting standards (for example TRIPOD-AI, CONSORT-AI)
  • Ethics, regulation, governance, and policy for health AI

Examples of in-scope work

The following examples illustrate the range of work the Journal publishes:

  • A clinical decision support model for sepsis early warning validated across multiple hospitals
  • An explainable deep learning model for chest radiograph triage
  • A federated learning framework for privacy-preserving training across hospital sites
  • A natural language processing pipeline for extracting outcomes from clinical notes
  • A fairness audit of a risk-prediction algorithm across patient subgroups
  • A multi-omics model for predicting treatment response in oncology
  • A remote monitoring analytics method using wearable sensor data
  • A systematic review of reporting quality in clinical prediction model studies

Out-of-scope and editorial discrimination

The Journal applies rigorous initial screening for scope-fit, methodological adequacy, and originality before sending manuscripts to peer review. The following categories of work are typically declined at desk-screen:

  • Bench biology, wet-lab, or clinical studies with no analytics, informatics, or computational dimension
  • Pure machine-learning methods with no healthcare application or clinical evaluation, which are better suited to the sibling journal Journal of Advanced Intelligent Computing and Informatics
  • Application papers whose primary contribution belongs to finance, business, or another applied field, which are better suited to the relevant sibling journals published by World Research Union
  • Clinical case reports or trial reports without a data, modeling, or informatics contribution
  • Method papers without adequate clinical validation, baselines, or reproducibility
  • Survey-style summaries without methodological synthesis or original analysis
  • Speculative commentary on health AI without an empirical or methodological component
  • Manuscripts reapplying standard models to standard datasets without a clear, generalizable contribution

Authors uncertain about scope-fit are encouraged to send a short pre-submission inquiry through the Contact page before preparing a full manuscript.

Article types

The Journal publishes the following article types. Detailed length, structure, and review expectations are described on the Author Guidelines page.

  • Original Research Article: full-length empirical, methodological, or theoretical contribution with original findings
  • Systematic or Methodological Review: structured synthesis following PRISMA, scientometric, bibliometric, or comparable established methodology
  • Short Communication: concise report of a focused finding, including thematic syntheses, brief methodological notes, and timely results of immediate interest
  • Editorial: by invitation only, authored by members of the Editorial Team or invited contributors

Particularly welcomed contributions

While the Journal accepts submissions across the full breadth of its subject domains, contributions in the following named sub-disciplines are particularly welcomed and align closely with the Journal's editorial expertise: clinical decision support, medical imaging and diagnostic AI, electronic health record and predictive analytics, precision medicine and genomic informatics, federated and privacy-preserving learning on health data, epidemiological and public health modeling, and the trustworthy and ethical deployment of clinical AI.